Gemini 2.5 Pro
OnlineFrontierClosedGoogle · Google DeepMind
google/gemini-2.5-pro
Google deep-reasoning model with massive context for research and multimodal pipelines.
Google deep-reasoning model with massive context for research and multimodal pipelines.
Strong at long documents, multi-step plans, and mixed media workflows. Routed through Cautus Intelligence so every token settles with transparent fee split on Litheum.
Weights and inference stay on the host. Cautus Intelligence meters the gateway; buyers never receive the raw endpoint credentials.
Provider-hosted capacity
Last heartbeat 10/11/2026, 4:19:10 PM
Frontier or open weights listed for unified billing; compute remains with the provider.
Lineage a buyer can click: base weights, license, fine-tune story, region, and custody. We do not invent eval scores. If no third-party card exists, the listing says so and still pins a card hash.
Strong at long documents, multi-step plans, and mixed media workflows. Routed through Cautus Intelligence so every token settles with transparent fee split on Litheum.
Mode: Open API
Open marketplace access. Usage metered per token and settled on Litheum.
No approval queue. Sign in for credits, create an mg_ key, and call this slug. Competitor domain blocks still apply if the host configured them.
This call → usage tx → settlement tx on Litheum. Platform take on this listing is 5.0% (Model + compute). Remainder goes to the model owner and, on matched jobs, the compute provider. Example at $1.25 / $10 per 1M: a 1M in + 1M out call costs $11.25.
Open Litheum explorer